Publication

• OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding
• ResVR: Joint Rescaling and Viewport Rendering of Omnidirectional Images
• 360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model
• Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts
• Null-Space Diffusion Sampling for Zero-Shot Point Cloud Completion
• EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding
• Panoptic Compositional Feature Field for Editable Scene Rendering with Network-Inferred Labels via Metric Learning
• More is better: Multi-source Dynamic Parsing Attention for Occluded Person Re-identification
• A Simple Visual-Textual Baseline for Pedestrian Attribute Recognition
• Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification
• Matching on Sets: Conquer Occluded Person Re-Identification Without Alignment